1/***************************************************************************
2 *                                  _   _ ____  _
3 *  Project                     ___| | | |  _ \| |
4 *                             / __| | | | |_) | |
5 *                            | (__| |_| |  _ <| |___
6 *                             \___|\___/|_| \_\_____|
7 *
8 * Copyright (C) Daniel Stenberg, <daniel@haxx.se>, et al.
9 *
10 * This software is licensed as described in the file COPYING, which
11 * you should have received as part of this distribution. The terms
12 * are also available at https://curl.se/docs/copyright.html.
13 *
14 * You may opt to use, copy, modify, merge, publish, distribute and/or sell
15 * copies of the Software, and permit persons to whom the Software is
16 * furnished to do so, under the terms of the COPYING file.
17 *
18 * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
19 * KIND, either express or implied.
20 *
21 * SPDX-License-Identifier: curl
22 *
23 ***************************************************************************/
24
25/* <DESC>
26 * Uses the "Streaming HTML parser" to extract the href pieces in a streaming
27 * manner from a downloaded HTML.
28 * </DESC>
29 */
30/*
31 * The HTML parser is found at https://github.com/arjunc77/htmlstreamparser
32 */
33
34#include <stdio.h>
35#include <curl/curl.h>
36#include <htmlstreamparser.h>
37
38
39static size_t write_callback(void *buffer, size_t size, size_t nmemb,
40                             void *hsp)
41{
42  size_t realsize = size * nmemb, p;
43  for(p = 0; p < realsize; p++) {
44    html_parser_char_parse(hsp, ((char *)buffer)[p]);
45    if(html_parser_cmp_tag(hsp, "a", 1))
46      if(html_parser_cmp_attr(hsp, "href", 4))
47        if(html_parser_is_in(hsp, HTML_VALUE_ENDED)) {
48          html_parser_val(hsp)[html_parser_val_length(hsp)] = '\0';
49          printf("%s\n", html_parser_val(hsp));
50        }
51  }
52  return realsize;
53}
54
55int main(int argc, char *argv[])
56{
57  char tag[1], attr[4], val[128];
58  CURL *curl;
59  HTMLSTREAMPARSER *hsp;
60
61  if(argc != 2) {
62    printf("Usage: %s URL\n", argv[0]);
63    return EXIT_FAILURE;
64  }
65
66  curl = curl_easy_init();
67
68  hsp = html_parser_init();
69
70  html_parser_set_tag_to_lower(hsp, 1);
71  html_parser_set_attr_to_lower(hsp, 1);
72  html_parser_set_tag_buffer(hsp, tag, sizeof(tag));
73  html_parser_set_attr_buffer(hsp, attr, sizeof(attr));
74  html_parser_set_val_buffer(hsp, val, sizeof(val)-1);
75
76  curl_easy_setopt(curl, CURLOPT_URL, argv[1]);
77  curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_callback);
78  curl_easy_setopt(curl, CURLOPT_WRITEDATA, hsp);
79  curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
80
81  curl_easy_perform(curl);
82
83  curl_easy_cleanup(curl);
84
85  html_parser_cleanup(hsp);
86
87  return EXIT_SUCCESS;
88}
89